ikawrakow/ik_llama.cpp
1
0
Fork 0
mirror of https://github.com/ikawrakow/ik_llama.cpp.git synced 2026-03-10 14:00:08 +00:00
Code Issues Packages Projects Releases Wiki Activity
Files
ef2b0066b9928c458942292b2084c4ebf6b0bf83
ik_llama.cpp/ggml
History
Iwan Kawrakow ef2b0066b9 On Zen4 repack fp16 models to bf16_r16 when run-time-repacking is requested 
This massively improves performance. As this is opt-in, we do not worry
about possible precision loss in the f16 -> bf16 conversion.
2025-01-21 19:14:57 +02:00
..
cmake
…
include
CPU Flash Attention improvements (#172)
2025-01-15 18:19:22 +02:00
src
On Zen4 repack fp16 models to bf16_r16 when run-time-repacking is requested
2025-01-21 19:14:57 +02:00
.gitignore
…
CMakeLists.txt
Move to c++17 projectwide (#80)
2024-10-04 14:43:26 +03:00